Message-ID: <1958160.rOz1oQAdlv@vostro.rjw.lan>
Date:	Fri, 09 Oct 2015 23:50:26 +0200
From:	"Rafael J. Wysocki" <rjw@...ysocki.net>
To:	Chen Yu <yu.c.chen@...el.com>
Cc:	pavel@....cz, tglx@...utronix.de, mingo@...hat.com, hpa@...or.com,
	bp@...en8.de, rui.zhang@...el.com, linux-pm@...r.kernel.org,
	x86@...nel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] [v4] x86, suspend: Save/restore extra MSR registers for suspend

On Thursday, August 27, 2015 11:18:27 AM Chen Yu wrote:
> A bug is reported(https://bugzilla.redhat.com/show_bug.cgi?id=1227208)
> that, after resumed from S3, CPU is running at a low speed.
> After investigation, it is found that, BIOS has modified the value
> of THERM_CONTROL register during S3, and changes it from 0 to 0x10,
> since value of 0x10 means CPU can only get 25% of the Duty Cycle,
> this triggers the problem.
> 
> Here is a simple scenario to reproduce the issue:
> 1.Boot up the system
> 2.Get MSR with address 0x19a, it should be 0
> 3.Put the system into sleep, then wake it up
> 4.Get MSR with address 0x19a, it should be 0(actually it shows 0x10)
> 
> Although this is a BIOS issue, it would be more robust for linux to deal
> with this situation. This patch fixes this issue by introducing a framework
> to save/restore specified MSR registers(THERM_CONTROL in this case)
> for suspend/resume.
> 
> When user encounters a problematic platform and needs to protect the
> MSRs during suspending, he can simply add a quirk entry in
> msr_save_dmi_table, and customizes MSR registers inside the quirk
> callback, for example:
> 
> u32 msr_id_need_to_save[] = {MSR_ID0, MSR_ID1, MSR_ID2...};
> 
> and the quirk mechanism ensures that, once resumed from suspended,
> the MSRs indicated by these IDs will be restored to their original values
> before suspended.
> 
> Since both 64/32-bit kernels are affected, this patch covers 64/32-bit
> common code path. And because the MSRs specified by the user might not
> be available or readable in any situation, we use rdmsrl_safe to safely
> save these MSRs.
> 
> Tested-by: Marcin Kaszewski <marcin.kaszewski@...el.com>
> Signed-off-by: Chen Yu <yu.c.chen@...el.com>
> ---
> v4:
>  - Revert v3 to v2, and fix some typos in changelog/comments. 
>    Use msr_info structure instead of msr_id + msr_value.
>    Adjust some codes for better readability.
> v3:
>  - Simplify the patch to only focus on THERM_CONTROL register.
>    This will make things 'just work'.
> v2:
>  - Cover both 64/32-bit common code path.
>    Use rdmsrl_safe to safely read MSR.
>    Introduce a quirk framework for save/restore specified MSR on different
>    platforms.
> ---
>  arch/x86/include/asm/suspend_32.h | 11 +++++
>  arch/x86/include/asm/suspend_64.h | 11 +++++
>  arch/x86/power/cpu.c              | 99 +++++++++++++++++++++++++++++++++++++++
>  3 files changed, 121 insertions(+)
> 
> diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
> index d1793f0..240aaa8 100644
> --- a/arch/x86/include/asm/suspend_32.h
> +++ b/arch/x86/include/asm/suspend_32.h
> @@ -9,12 +9,23 @@
>  #include <asm/desc.h>
>  #include <asm/fpu/api.h>
>  
> +struct msr_type {

I'd call this msr_data.

> +	bool msr_saved;
> +	struct msr_info rv;
> +};
> +
> +struct saved_msr {

And this msr_context.

> +	unsigned short num;
> +	struct msr_type *msr_array;
> +};
> +
>  /* image of the saved processor state */
>  struct saved_context {
>  	u16 es, fs, gs, ss;
>  	unsigned long cr0, cr2, cr3, cr4;
>  	u64 misc_enable;
>  	bool misc_enable_saved;
> +	struct saved_msr msr_for_save;

"msr_to_save"?

>  	struct desc_ptr gdt_desc;
>  	struct desc_ptr idt;
>  	u16 ldt;
> diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
> index 7ebf0eb..40a7a00 100644
> --- a/arch/x86/include/asm/suspend_64.h
> +++ b/arch/x86/include/asm/suspend_64.h
> @@ -9,6 +9,16 @@
>  #include <asm/desc.h>
>  #include <asm/fpu/api.h>
>  
> +struct msr_type {
> +	bool msr_saved;
> +	struct msr_info rv;
> +};
> +
> +struct saved_msr {
> +	unsigned short num;
> +	struct msr_type *msr_array;
> +};

The definitions look the same as the previous ones.

Can we share them somehow?

> +
>  /*
>   * Image of the saved processor state, used by the low level ACPI suspend to
>   * RAM code and by the low level hibernation code.
> @@ -24,6 +34,7 @@ struct saved_context {
>  	unsigned long cr0, cr2, cr3, cr4, cr8;
>  	u64 misc_enable;
>  	bool misc_enable_saved;
> +	struct saved_msr msr_for_save;
>  	unsigned long efer;
>  	u16 gdt_pad; /* Unused */
>  	struct desc_ptr gdt_desc;
> diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
> index 9ab5279..8442473 100644
> --- a/arch/x86/power/cpu.c
> +++ b/arch/x86/power/cpu.c
> @@ -23,6 +23,7 @@
>  #include <asm/debugreg.h>
>  #include <asm/cpu.h>
>  #include <asm/mmu_context.h>
> +#include <linux/dmi.h>
>  
>  #ifdef CONFIG_X86_32
>  __visible unsigned long saved_context_ebx;
> @@ -32,6 +33,30 @@ __visible unsigned long saved_context_eflags;
>  #endif
>  struct saved_context saved_context;
>  
> +static void msr_save_context(struct saved_context *ctxt)
> +{
> +	int i = 0;
> +
> +	for (i = 0; i < ctxt->msr_for_save.num; i++) {
> +		struct msr_type *msr = &ctxt->msr_for_save.msr_array[i];
> +
> +		msr->msr_saved = !rdmsrl_safe(msr->rv.msr_no,
> +			&msr->rv.reg.q);
> +	}

If you did something like

	struct msr_type *msr = ctxt->msr_for_save.msr_array;
	struct msr_type *end = msr + ctxt->msr_for_save.num;

	while (msr < end) {
		msr->msr_saved = !rdmsrl_safe(msr->rv.msr_no, &msr->rv.reg.q);
		msr++;
	}

here (and analogously below), it would be somewhat easier to follow IMO.

> +}
> +
> +static void msr_restore_context(struct saved_context *ctxt)
> +{
> +	int i = 0;
> +
> +	for (i = 0; i < ctxt->msr_for_save.num; i++) {
> +		struct msr_type *msr = &ctxt->msr_for_save.msr_array[i];
> +
> +		if (msr->msr_saved)
> +			wrmsrl(msr->rv.msr_no, msr->rv.reg.q);
> +	}
> +}
> +
>  /**
>   *	__save_processor_state - save CPU registers before creating a
>   *		hibernation image and before restoring the memory state from it
> @@ -111,6 +136,7 @@ static void __save_processor_state(struct saved_context *ctxt)
>  #endif
>  	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
>  					       &ctxt->misc_enable);
> +	msr_save_context(ctxt);
>  }
>  
>  /* Needed by apm.c */
> @@ -229,6 +255,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
>  	x86_platform.restore_sched_clock_state();
>  	mtrr_bp_restore();
>  	perf_restore_debug_store();
> +	msr_restore_context(ctxt);
>  }
>  
>  /* Needed by apm.c */
> @@ -320,3 +347,75 @@ static int __init bsp_pm_check_init(void)
>  }
>  
>  core_initcall(bsp_pm_check_init);
> +
> +/* We constrain the number of MSRs to 64. */

Why 64 in particular?

> +#define MAX_MSR_SAVED	64
> +
> +static struct msr_type msr_context_array[MAX_MSR_SAVED];

I wonder if this array may be allocated dynamically?

We'll waste memory here in the majority of cases.

> +
> +/*
> + * Following section is a quirk framework for problematic BIOS:

"The following ..."

> + * Sometimes MSRs are modified by BIOS after suspended to
> + * ram, this might cause unexpected behavior after resumed.

"RAM" (in capitals) and "during resume" or "after wakeup".

> + * Thus we save/restore these specified MSRs during suspending
> + * in order to work around it.
> + * A typical bug is reported at:
> + * https://bugzilla.redhat.com/show_bug.cgi?id=1227208
> + */
> +static int msr_set_info(const u32 *msr_id, const int total_num)

I'd call it "msr_init_context" or something like that.

> +{
> +	int i = 0;
> +
> +	if (total_num > MAX_MSR_SAVED) {
> +		pr_err("PM: too many MSRs need to be saved.\n");
> +		return -EINVAL;
> +	}
> +	if ((NULL != saved_context.msr_for_save.msr_array) ||

if (saved_context.msr_for_save.msr_array || saved_context.msr_for_save.num > 0) {

> +	     0 != saved_context.msr_for_save.num) {
> +		pr_err("PM: quirk already applied, please check your dmi match table.\n");
> +		return -EINVAL;
> +	}
> +	for (i = 0; i < total_num; i++) {
> +		msr_context_array[i].rv.msr_no = msr_id[i];
> +		msr_context_array[i].msr_saved = false;
> +		msr_context_array[i].rv.reg.q = 0;
> +	}
> +	saved_context.msr_for_save.num = total_num;
> +	saved_context.msr_for_save.msr_array = msr_context_array;
> +	return 0;
> +}
> +
> +/*
> + * For any further problematic BIOS/platforms,
> + * please add your own function similar to msr_initialize_bdw.
> + */
> +static int msr_initialize_bdw(const struct dmi_system_id *d)
> +{
> +	/* Add any extra MSR ids into this array. */
> +	u32 bdw_msr_id[] = {MSR_IA32_THERM_CONTROL};
> +
> +	pr_info("PM: %s detected, MSR saving is needed during suspending.\n",
> +		d->ident);
> +	return msr_set_info(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
> +}
> +
> +static struct dmi_system_id msr_save_dmi_table[] = {
> +	{
> +	 .callback = msr_initialize_bdw,
> +	 .ident = "BROADWELL BDX_EP",
> +	 .matches = {
> +		DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
> +		DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"),
> +		DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"),
> +		},
> +	},
> +	{}
> +};
> +
> +static int pm_check_save_msr(void)
> +{
> +	dmi_check_system(msr_save_dmi_table);
> +	return 0;
> +}
> +
> +late_initcall(pm_check_save_msr);

Thanks,
Rafael

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists